| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1446540880503147, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5696774193548387, | |
| "eval_loss": 0.19738028943538666, | |
| "eval_runtime": 5.6204, | |
| "eval_samples_per_second": 551.558, | |
| "eval_steps_per_second": 11.565, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 0.5302301645278931, | |
| "learning_rate": 1.4758909853249476e-05, | |
| "loss": 0.3128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8087096774193548, | |
| "eval_loss": 0.10058140009641647, | |
| "eval_runtime": 6.1392, | |
| "eval_samples_per_second": 504.95, | |
| "eval_steps_per_second": 10.588, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8661290322580645, | |
| "eval_loss": 0.07083548605442047, | |
| "eval_runtime": 5.6445, | |
| "eval_samples_per_second": 549.204, | |
| "eval_steps_per_second": 11.516, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 0.4523966312408447, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.1161, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1908, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 260941334653608.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.6947875151517261, | |
| "num_train_epochs": 6, | |
| "temperature": 17 | |
| } | |
| } | |